5 papers
Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models
Chashi Mahiul Islam, Alan Villarreal, Mao Nishino +2
As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical instability has emerged as a critical reliability…
Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent
Sajib Biswas, Mao Nishino, Samuel Jacob Chacko +1
As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall su…
Adversarial Attack on Large Language Models using Exponentiated Gradient Descent
Sajib Biswas, Mao Nishino, Samuel Jacob Chacko +1
As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are ali…
Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers
Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino +1
While transformer-based models dominate NLP and vision applications, their underlying mechanisms to map the input space to the label space semantically are not well understood. In…
Unaligning Everything: Or Aligning Any Text to Any Image in Multimodal Models
Shaeke Salman, Md Montasir Bin Shams, Xiuwen Liu
Utilizing a shared embedding space, emerging multimodal models exhibit unprecedented zero-shot capabilities. However, the shared embedding space could lead to new vulnerabilities i…